Show HN: Visually orchestrate Claude Code AI agents RondoFlow launched as an open-source, invite-only tool that lets users visually orchestrate teams of Claude Code agents on a drag-and-drop React Flow canvas, running locally via npm or Docker. The tool spawns Claude Code CLI subprocesses as agents that can read and write files, run commands, and use MCP tools, with a Director, Planner, and Advisor steering each run and a three-layer safety model gating risky actions. RondoFlow also supports mixing Claude Code, OpenAI, and Perplexity agents in one workflow and ships as five Docker containers on ports 5432, 3001, 3000, and 3002. Build teams of Claude Code agents - visually. Describe what you need on a drag-and-drop canvas, and RondoFlow assembles a team of specialized AI agents that plan, run, and improve the work together - locally, on your machine, with your files. Most "AI workflow" tools wire prompts together. RondoFlow orchestrates real Claude Code https://docs.anthropic.com/en/docs/claude-code agents - so the agents on your canvas can actually read and write files, run commands, and use MCP tools and skills, all governed by safety policies you control. You compose them visually, hit Run , and watch the team execute in real time. Why it's different - 🧩 Visual multi-agent canvas - drag agents, skills, safety rules, resources, and MCP connections onto a React Flow https://reactflow.dev board and connect them into a workflow. - 🤖 Real agents that do things - agents are Claude Code CLI subprocesses, not just chat completions. They edit code, run tools, and stream their work back live. - 🎯 AI that steers the run - a Director evaluates each step mid-run and decides whether to continue, retry, or conclude; a Planner tunes the team before it starts; an Advisor reviews the result afterward. - 🔌 Multi-provider - mix Claude Code local CLI , OpenAI , and Perplexity agents in the same workflow. - 🔒 Local-first & policy-governed - runs on your machine, talks to your files, and gates risky actions behind a three-layer safety model. Nothing leaves your box except the model API calls you configure. git clone https://github.com/rondoflow/rondoflow.git cd rondoflow npm run setup installs deps, generates .env, starts Postgres, migrates + seeds npm run dev opens at http://localhost:3000 git clone https://github.com/rondoflow/rondoflow.git cd rondoflow cp .env.example .env edit .env see Configuration below docker compose up builds and starts all services This starts five containers: | Container | Port | Role | |---|---|---| | rondoflow-postgres | 5432 | PostgreSQL database | | rondoflow-server | 3001 | Fastify backend + Socket.IO + Claude Code CLI | | rondoflow-ui | 3000 | Next.js frontend | | rondoflow-docs | 3002 | Nextra documentation site proxied at /docs | | rondoflow-migrate | - | Runs database migrations once, then exits | Then open http://localhost:3000 http://localhost:3000 . Docker mode needs Docker Desktop only - Node.js is not required on the host. RondoFlow is invite-only - open self-registration is disabled, and an admin creates all accounts. Set RONDOFLOW ADMIN EMAIL and RONDOFLOW ADMIN PASSWORD in .env before you run setup; the seed step then bootstraps that first admin it's skipped if either is blank . - Option A local : npm run setup runs the seed for you, so the admin is created automatically. - Option B Docker : the rondoflow-migrate container runs migrations only - run the seed step yourself npm run db:seed , with the admin vars set and Postgres reachable to create the first admin. Sign in with that account email/password . On first sign-in a short onboarding wizard walks you through picking a working directory and a work mode Quick Start - describe a task and let RondoFlow build the team - or Full Control - assemble agents by hand . Admins can then create accounts for teammates from the Users panel. If the Claude Code CLI isn't detected, the app shows install instructions and waits. Drag nodes onto an interactive board and connect them to define how work flows. Everything auto-saves. | Node types | Assistants agents , Skills, Safety Rules, Resources, Connections MCP , Output, Condition branching , Sticky Notes | | Connections | Flow edges execution order , association edges configuration , and conditional edges branching from a Condition node | | Interaction | Drag-and-drop palette, undo/redo Ctrl+Z , keyboard shortcuts ? , command palette Ctrl+K | | Workspaces | Multiple project-based workspaces, each tied to a folder on your machine; export/import to share | Each Assistant has a provider, model, personality, skills, memory, and MCP connections - all configurable from the side panel. | Provider | Models | Notes | |---|---|---| | Claude Code default | Opus / Sonnet / Haiku tiers | Runs the local CLI; full tool, MCP, and skill access | | OpenAI | GPT / o-series | API-based; optional web search | | Perplexity | Sonar family | API-based; web-grounded research | The Workflow Generator picks a sensible model per agent automatically - you can always change it. Three AI helpers reason about your run at different points: - Planner before - reviews the team, models, skills, and order; suggests improvements up front. - Director during - after each step, decides continue / redirect retry with sharper instructions / conclude , with a tunable criticism level and learnings it banks for next time. - Advisor after - compares the result against the objective and offers one-click fixes. Multiple Assistants brainstorm, review, or debate a topic while an automated Facilitator manages turn order and synthesizes a conclusion. Describe a task in plain English and RondoFlow designs a 2–5 agent workflow with personas, models, and skills, laid out as a DAG. Review and edit it before it hits the canvas - or start from a built-in template Code Review, Content Team, Research, Brainstorm . Skills are reusable instruction sets that give Assistants specialized abilities. RondoFlow ships built-in skills Code Review, Writing Assistant, Data Analysis, API Designer, Test Writer and you can install more from any Git repository. Three layers of policies - global , per-agent , and per-session - control what agents may do. The most restrictive policy always wins, risky commands require your approval, and budget limits prevent runaway costs. See SECURITY.md https://github.com/rondoflow/rondoflow/blob/master/SECURITY.md for the full model. RondoFlow runs as a shared team workspace with three global roles: viewer read-only , editor create, edit, delete, and run workflows - Director / Planner / Advisor / Discussions included , and admin everything an editor can do, plus user management and global settings . Accounts are invite-only - admins create users with a starting role from a Users panel and can change roles or deactivate/remove accounts; there is no open self-registration. Roles are enforced server-side on both the REST API and the realtime socket layer viewers get a read-only canvas - palette hidden, nodes locked , and the UI mirrors those capabilities to hide affordances a role can't use. Admin user-management actions are written to the audit log. Recurring Schedules cron , iterative Loops re-run an agent until a goal is met , an in-app Git panel status, branches, commit, push , Memory that persists facts across runs, external folder mounts, and an audit log + analytics dashboard for monitoring and cost tracking. 1. Describe what you need in plain English - or pick a template. 2. Review the AI-generated team of agents with their providers, models, and skills. 3. Run the workflow on the canvas - watch agents execute in real time, with the Director steering between steps. 4. Improve with Advisor analysis and one-click suggestions after each run. php flowchart TD A "Describe your task